Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add somnus0x/agt-skill-pack --skill factory-reviewgit clone --depth 1 https://github.com/somnus0x/agt-skill-packWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/somnus0x/agt-skill-pack/factory-review)<a href="https://agentmods.dev/skills/somnus0x/agt-skill-pack/factory-review"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/factory-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/somnus0x/agt-skill-pack/factory-review"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/factory-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01559 |
| Opus 5.5 | $0.00020 | $0.00624 |
| Sonnet 5.5 | $0.00010 | $0.00312 |
| Haiku 4.5 | $0.00005 | $0.00156 |
Grade A, and why
factory-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factory Review — Cross-Model Adversarial Critique
Use a different AI model to review anything your primary AI produced. Same-model self-review falls into local minima. A different model catches different blind spots.
Why
Claude reviewing Claude's output has predictable blind spots. GPT reviewing Claude (or vice versa) catches what the original model was trained to overlook. Two-model review (executor + critic) produces better output than self-play.
How to use
Option A — Two chat windows:
- Draft something in your primary AI (Claude, GPT, Gemini, etc.)
- Open a different AI in another tab
- Paste the relevant review prompt below + your draft
- Read the review, apply what's valid, ignore what's noise
Option B — CLI tools (advanced): If you have access to multiple AI CLIs (Claude Code, Codex, droid, etc.), you can pipe content directly. See the CLI section at the bottom.
Review Modes
1. Content Review (posts, threads, copy, docs)
Paste this into a different AI than the one that wrote your draft:
You are a critical reviewer for developer-audience content.
Review the following draft. Be adversarial — your job is to find problems, not praise.
Check for:
1. **Unsupported claims** — any numbers, benchmarks, or assertions without evidence?
2. **Missing context** — what would a developer reading this need to know that's not here?
3. **Logical gaps** — does the argument flow? Any leaps?
4. **Shareability blockers** — what would stop someone from sharing this? Too niche? Too vague?
5. **Voice drift** — does anything sound like marketing copy instead of a developer talking to peers?
6. **Factual errors** — any technical claims that are wrong or outdated?
Format your review as:
- VERDICT: [SHIP / REVISE / KILL] with one-line reason
- ISSUES: numbered list, severity (critical/medium/minor) for each
- STRONGEST PART: what works and why
- SUGGESTED FIX: for each critical/medium issue, a concrete rewrite suggestion
DRAFT:
---
[PASTE YOUR CONTENT HERE]
---
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 188 lines · 51 tokens per session scan A f0ed17c77135
factory-review is a skill published in the GitHub repository somnus0x/agt-skill-pack (74 stars, last pushed 18d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,559 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…